Friday, May 12, 2017

Hack #27 #OpenWERX Data Science #Hackathon @SOFWERX

#OpenWERX Data Science #Hackathon @SOFWERX
Date: May12-13 2017

#OpenWERX Data Science #Hackathon @SOFWERKS

First event of #SOFIC2017 taking place in Tampa, Florida.

Team: Social Media Data Science GrowthHack

Team Members: Chima Nwala, Angelique Robateau and Houssein Farah




A post shared by RuckSackHack (@rucksackhack) on
Challenge # 2 – Master Marven An Expert … Not an Expert…. What is the difference Use Analytics to determine who is (or who is not a ‘Novel Solution Material Science’



Team’s Hackathon Methodology

Understand the Challenge Understand the Problem Set

Questions and Draft Modeling Data Extraction Tools – R Web Scrapping

Data Extraction and Cleaning Machine Learning Data Analysis - Visualization Results

A post shared by RuckSackHack (@rucksackhack) on
Hypothesis: An expert in Material Science is based on the max number of citations. Research Content Team googled ‘ Top Material Scientist in the world & Material Science Journal’




Many results Selected ‘ Journal Ranking on Material Science’ 2015 data of top Material Scientist in the world. – approximately 550 By # of Citation By # of References Understanding the Challenge Challenge # 2 – Master Marven An Expert … Not an Expert…. What is the difference? Use any source (e.g. LinkedIn to identify an expert in Material Science’



Hypothesis Testing

The number 1 expert in Material Science based on the number of Journal or citation is in the USA. Use Analytics to determine who is (or who is not a ‘Novel Solution Material Science’ Data Extraction, Cleaning, Machine Learning Team googled ‘ Top Material Scientist in the world & Material Science Journal’ Many results Selected ‘ Journal Ranking on Material Science’ 2015 data of top Material Scientist in the world. – approximately 550 ( no names) By # of Citation By # of References Stored Data in open source – Gitbub.com Create ‘R’ Script Convert Journal Ranking Material Science file to CSV File required no further cleansing Run ‘R’ Script Some Data was masked Run second R script – against Ranking File – match on Ref/Doc and Citation Ran Summary Statistics of the Data Set (Ranking) Results – Top 6 countries with the most material scientists.

For it's work the team received a signed copy of the book R for Everyone, Advanced Analytics and Graphics by Jared P. Lander



A post shared by RuckSackHack (@rucksackhack) on

Sunset on Clearwater Beach

via IFTTT